Scheduled Tasks

Run your agents automatically on a recurring schedule

Overview

Scheduled Tasks let you run any agent automatically on a recurring schedule. Create a task in Control Hub, pick an agent, write a prompt, set a schedule, and let it run on its own. Every execution starts a new conversation with the agent, just like sending a message manually.

How It Works

1. Create the task

   You create a scheduled task with an agent, a prompt (the message to send), and a schedule.

2. Aster checks what's due

   Aster runs a job every minute that checks which tasks are due.

3. The prompt is sent

   When a task is due, it sends the prompt to the agent as a new conversation.

4. The agent runs

   The agent runs with all its tools, knowledge bases, and capabilities — just like an interactive chat.

5. The conversation appears

   The resulting conversation appears in the dashboard with source scheduled-task.

Creating a Scheduled Task

From Control Hub

1. Open Scheduled Tasks

   Go to Control Hub → Tasks and click Create Task.

2. Fill in the form

   • Task Name: A descriptive name (e.g., “Daily VP Candidate Digest”)
   • Agent: Select which agent should run
   • Description: Optional notes about what this task does
   • Schedule: Use a preset or write a custom cron expression
   • Prompt: The message the agent will receive when the task runs
3. Create the task

   Click Create Task. The task starts enabled by default and will run on its next scheduled time.

From a Conversation (Manage Scheduled Tasks tool)

Agents with the manage_scheduled_tasks tool enabled can create scheduled tasks during conversations. Just ask:

• “Check stock prices every morning at 9 AM”
• “Send me a weekly summary of new candidates every Monday”
• “Run a daily report and email it to the team”

The agent will create the scheduled task for you. Enable the manage_scheduled_tasks tool in your agent’s configuration under Tools.

Schedule Options

Presets

Click a button under Quick Presets in the task form, or type one of these names into the schedule field. Times are UTC:

Preset	Cron Expression	When It Runs
Hourly	0 * * * *	Every hour on the hour
Daily	0 9 * * *	Every day at 9:00 AM UTC
Weekly	0 9 * * 1	Every Monday at 9:00 AM UTC
Monthly	0 9 1 * *	1st of every month at 9:00 AM UTC
Every 15 Minutes	*/15 * * * *	Every 15 minutes
Every 30 Minutes	*/30 * * * *	Every 30 minutes
Twice Daily	0 9,21 * * *	9:00 AM and 9:00 PM UTC
Weekdays	0 9 * * 1-5	Monday through Friday at 9:00 AM UTC
Weekends	0 10 * * 0,6	Saturday and Sunday at 10:00 AM UTC

Custom Cron Expressions

For more control, enter a standard 5-part cron expression:

┌───────────── minute (0–59)
│ ┌───────────── hour (0–23)
│ │ ┌───────────── day of month (1–31)
│ │ │ ┌───────────── month (1–12)
│ │ │ │ ┌───────────── day of week (0–7, where 0 and 7 = Sunday)
│ │ │ │ │
* * * * *

Examples:

Expression	Meaning
0 18 * * *	Every day at 6:00 PM
0 8 * * 1-5	Weekdays at 8:00 AM
0 9 15 * *	15th of every month at 9:00 AM
*/10 * * * *	Every 10 minutes
0 9,12,17 * * *	9:00 AM, 12:00 PM, and 5:00 PM daily

A Schedule Preview under the field describes simple schedules in plain English, such as “Daily at 9:00 AM”. Other expressions are shown as written.

Schedules are stored and run in UTC, and the task form takes UTC times. When you ask an agent to schedule a task (“every weekday at 9am”), it converts your local time to UTC using your time zone’s current offset and tells you the UTC schedule it saved. Runs then shift by an hour in local time when daylight saving time changes. If a schedule can’t be converted exactly, the agent asks you to give it in UTC or split it into separate tasks.

Managing Tasks

Enable / Disable

Toggle any task on or off with the switch in the task list. Disabled tasks won’t run but keep their configuration and history.

Run Now

Trigger any enabled task immediately from the actions menu (three dots → Run Now). This creates a new execution just like a scheduled run.

Edit

Update the name, agent, prompt, or schedule of any task. Changes take effect on the next scheduled run.

Delete

Remove a task permanently. Execution history is preserved for reference.

Admin View

Organization admins can toggle Admin View to see all scheduled tasks across the organization, not just their own.

Execution History

Click View History in the task’s actions menu to see past executions:

• Status: Running, Completed, or Failed
• Timestamps: When each execution started
• Conversation Links: Click through to the conversation created by each run
• Stats: Total runs, completed, failed, and success rate

History shows the 50 most recent runs.

Use Cases

Daily Digest Emails

Create a task that runs daily and emails a summary to your team.

Task prompt example:

Search the "2026 Candidate Resumes" knowledge base for any resumes uploaded today.
For each new candidate, provide the standard summary (name, firm, education, fit assessment).
Flag any Strong Fit candidates at the top.
Email the digest to [e-mail], [e-mail], and [e-mail].
Subject: "Candidate Search Daily Digest"
If no new candidates were uploaded today, send a brief email confirming that.

Recurring Reports

Have an agent query your database and generate a report on a schedule.

Task prompt example:

Pull this week's sales data from the Snowflake database.
Compare to last week and highlight any significant changes.
Generate a PowerPoint with the key charts and email it to the sales team.

Monitoring & Alerts

Schedule an agent to check for issues and notify your team.

Task prompt example:

Check the support knowledge base for any new tickets tagged "urgent" in the last hour.
If there are any, summarize them and email the on-call team at [e-mail].
If none, do nothing.

Combining with Other Features

Scheduled tasks work with all agent capabilities:

Combine With	What You Can Do
Knowledge Bases	Search for new documents, analyze content, generate reports
Email Tool	Send digest emails, alerts, or reports to your team
Database Queries	Pull fresh data from Postgres or Snowflake on a schedule
Multi-Agent Workflows	Kick off a chain of agents that collaborate on a task
Web Search	Monitor news, competitors, or market changes
Python Execution	Run data analysis scripts and generate visualizations

Best Practices

1. Write clear, specific prompts. The agent receives only the prompt text — it doesn’t have context from previous runs. Include all the instructions it needs in the prompt itself.
2. Use the right schedule frequency. Don’t run tasks more often than needed. A daily digest doesn’t need to run every 15 minutes.
3. Test with Run Now first. Before relying on the schedule, use Run Now to verify the agent produces the output you expect.
4. Check execution history. Review past runs periodically to catch failures or unexpected behavior.
5. Include error handling in prompts. Tell the agent what to do when there’s nothing to report (e.g., “If no new data, send a brief confirmation email instead”).